Can I read Tamil Language Handwritten Document Digitization and Analysis of the Impact of Data Augmentation Using Generative Adversarial Networks (GANs) on the Accuracy of CNN Model on EtoBox?

Tamil Language Handwritten Document Digitization and Analysis of the Impact of Data Augmentation Using Generative Adversarial Networks (GANs) on the Accuracy of CNN Model by Venkatesh Murugesh; Aditya Parthasarathy; Gokul P. Gopinath; Anindita Khade is a book available to read on EtoBox.

What is Tamil Language Handwritten Document Digitization and Analysis of the Impact of Data Augmentation Using Generative Adversarial Networks (GANs) on the Accuracy of CNN Model about?

Recognition of handwritten documents is an essential part of today's world for various reasons such as analysis, data extraction, etc. Recognition of handwritten in Indian regional languages, for, e.g., Tamil character is very difficult, due to variations in size, style, and orientation angle. Limited availability of handwritten character dataset makes it difficult to achieve high accuracy for all the characters present in the language. In this paper, we propose a deep learning approach to recognize and classify handwritten characters of the Tamil language. The proposed system can be divided into five phases: expansion of the dataset and data augmentation with the help of Generative Adversarial Networks (GAN), preprocessing of the input image to reduce the noise, segmentation of the characters, feature extraction, and classification of the character done using Convolutional Neural Networks (CNN). We have achieved an accuracy of 94.03% and with data augmentation using GAN, an accuracy of 97% was achieved. The proposed system, along with the recognition of characters, also converts the image of the handwritten document into an editable word document or a PDF file.

Author

Venkatesh Murugesh; Aditya Parthasarathy; Gokul P. Gopinath; Anindita Khade

Publisher

Springer Singapore : Imprint: Springer

Published

2022

Language

EN

ISBN

9789811679957

Subjects

Mathematics, Engineering, Computer Science